Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add xonika9/agent-skills --skill x9-idea-criticgit clone --depth 1 https://github.com/xonika9/agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/xonika9/agent-skills/x9-idea-critic)<a href="https://agentmods.dev/skills/xonika9/agent-skills/x9-idea-critic"><img src="https://agentmods.dev/badge/skills/xonika9/agent-skills/x9-idea-critic/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/xonika9/agent-skills/x9-idea-critic"><img src="https://agentmods.dev/badge/skills/xonika9/agent-skills/x9-idea-critic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00078 | $0.01920 |
| Opus 5 | $0.00039 | $0.00960 |
| Sonnet 5 | $0.00016 | $0.00384 |
| Haiku 4.5 | $0.00008 | $0.00192 |
Grade A, and why
x9-idea-critic scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Idea critic
Criticize through the routes the user selected. Claude and GPT are independent perspectives with different error profiles; neither route is a fallback or a quality tier. Route names identify providers, not the currently selected models.
The machine-readable onboarding contract lists external prerequisites.
Select mode
For /x9-idea-critic [mode] [idea], treat the first argument as a mode only when it is one of the recognized words below. Otherwise it is part of the idea. Natural-language requests map to the same modes.
When the invocation omits the idea, recover the latest clearly discussed proposal, intended outcome, success criterion, and known constraints from the conversation. Ask one short question only when the conversation leaves the target idea ambiguous.
| Mode | Natural-language examples | Critics |
|---|---|---|
| default / omitted | «раскритикуй идею», «проверь на прочность» | one fresh Claude critic and one fresh GPT critic |
claude |
«раскритикуй через Claude» | one fresh Claude critic |
gpt |
«спроси GPT», «раскритикуй через GPT» | one fresh GPT critic |
full |
«разнеси по полной», «панель критиков» | one critic from each provider for each of 2–3 declared lenses |
For full, select and declare exactly two or three applicable lenses before dispatch from feasibility/execution, user or market demand, and devil's-advocate/simpler alternative. Tell the user that this mode is slower and heavier, then start one critic per declared lens/provider pair as host capacity permits. That declared matrix is the completion boundary.
Sealed brief
Before dispatch, collect the load-bearing evidence into one sealed packet. Give every critic the same factual packet:
- the proposal in neutral language;
- intended user/outcome and observable success criterion;
- known constraints and an evidence packet containing the relevant content or excerpt, its source path or URL as provenance, retrieval time when freshness matters, whether the packet includes the full source or an excerpt, and any extraction limits;
- the critic's job: identify invalidating assumptions, failure modes, relevant competition, a cheaper or simpler path to the same outcome, the most likely practical cause of failure, and the cheapest disconfirming tests;
- required output:
KILLER,SERIOUS,MINOR, evidence/uncertainty, and a verdict.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago Changed · +13 lines 407700109a21
- 11d ago First seen · 80 lines · 78 tokens per session scan A f62409c0187d
x9-idea-critic is a skill published in the GitHub repository xonika9/agent-skills (4 stars, last pushed 6d ago), licensed MIT. It adds 78 tokens to every session and 1,920 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
e2e-automator
Build robust end-to-end test suites with Playwright or Cypress. Covers page objects, fixtures, visual testing, and CI integration.
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
architecture-decision-records
Comprehensive patterns for creating, maintaining, and managing Architecture Decision Records (ADRs) that capture the context and rationale behind significant technical decisions.
agent-framework-azure-ai-py
Build persistent agents on Azure AI Foundry using the Microsoft Agent Framework Python SDK.
api-security
Authorized security assessment of REST, GraphQL, WebSocket, and SOAP APIs: discovery, authentication and authorization flaws (BOLA/IDOR, JWT/OAuth), rate-limit testing, and a structured multi-phase methodology.
aria
Designs the data model, API contracts, and structural foundation of the system.